Cross-Sectional Industrialization Factors’ Contribution to Heat Wave Risk Classification

The intensifying frequency and severity of heatwaves, driven by climate change, pose significant threats to human health, agriculture, and ecosystems, especially in industrialized regions. Traditional studies on heatwave risk often focus on meteorological variables, while neglecting the influence of industrialization and urbanization. This paper addresses this gap by employing advanced machine learning models, specifically Multi-Layered Perceptron (MLP) and Support Vector Machine (SVM), and Logistic Regression (LR) to analyze the relationship between industrialization factors and heatwave risk across California's diverse census tracts. Using data from the National Risk Index (NRI) and the Smart Location Database (SLD), we found that the MLP model, which achieved a cross-validation accuracy of 94.81%, outperformed the SVM and LR models in capturing the impact of industrial metrics such as employment density, land use, and proximity to transit on heatwave vulnerability. Our results reveal the significant role industrialization plays in exacerbating heatwave risk, particularly in urban areas affected by the Urban Heat Island effect. These findings suggest that integrating industrialization factors into heat wave risk assessments is essential for protecting vulnerable communities and guiding more effective urban planning.